Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4000 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0712. Min Act: -0.0001

Data Index: 635643 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0751. Min Act: -0.0001

Data Index: 817688 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0752. Min Act: -0.0001

Data Index: 425169 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0711. Min Act: -0.0001

Data Index: 722422 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0734. Min Act: -0.0000

Data Index: 197420 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0666. Min Act: -0.0001

Data Index: 763549 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0759. Min Act: -0.0001

Data Index: 658752 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1305891 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0673. Min Act: -0.0000

Data Index: 444185 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0630. Min Act: -0.0001

Data Index: 616374 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1335012 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1339299 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0588. Min Act: -0.0000

Data Index: 105907 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0566. Min Act: -0.0001

Data Index: 345178 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0492. Min Act: -0.0001

Data Index: 881659 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0491. Min Act: -0.0000

Data Index: 697758 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0522. Min Act: -0.0000

Data Index: 711174 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0481. Min Act: -0.0000

Data Index: 259593 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0558. Min Act: -0.0001

Data Index: 976018 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1279352 (C4 (Web Text))

Max Activating Token Index: 421